Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Community Extraction in Multilayer Networks with Heterogeneous Community Structure
Authors: James D. Wilson, John Palowitch, Shankar Bhamidi, Andrew B. Nobel
JMLR 2017 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We investigate the performance of Multilayer Extraction on three applications and a test bed of simulations. Our theoretical and numerical evaluations suggest that Multilayer Extraction is an effective exploratory tool for analyzing complex multilayer networks. |
| Researcher Affiliation | Academia | James D. Wilson EMAIL Department of Mathematics and Statistics University of San Francisco San Francisco, CA 94117-1080 John Palowitch EMAIL Shankar Bhamidi EMAIL Andrew B. Nobel EMAIL Department of Statistics and Operations Research University of North Carolina at Chapel Hill Chapel Hill, NC 27599 |
| Pseudocode | No | The paper describes the Multilayer Extraction procedure in Section 5, breaking it down into Initialization, Extraction (Layer Set Search, Vertex Set Search), and Refinement steps. However, these steps are described in continuous paragraph text without being formatted as a distinct pseudocode block or algorithm figure. |
| Open Source Code | Yes | Publicly available code is available at https://github.com/jdwilson4/Multilayer Extraction. |
| Open Datasets | Yes | We investigate three multilayer networks of various size, sparsity, and relational types: a social network from an Austrailian computer science department (Han et al., 2014); an air transportation network of European airlines (Cardillo et al., 2013); and a collaboration network of network science authors on arXiv.org (De Domenico et al., 2014). |
| Dataset Splits | No | The paper describes generating synthetic data for simulation studies (e.g., "generated multilayer stochastic block models", "Erdos-Renyi random graphs") and specifies how parameters were varied in these generated datasets. For the real-world applications, it applies the Multilayer Extraction procedure to the full networks. It does not provide explicit training/test/validation splits for any dataset used to reproduce experiments in a supervised or cross-validation context. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to run the experiments, such as CPU models, GPU models, or memory specifications. |
| Software Dependencies | Yes | For the first four methods, we use the default settings from the igraph package version 0.7.1 set in R. ... We use the MATLAB implementation from (Jutla et al., 2011) of Gen Louvain ... We use the C++ multiplex implementation of Infomap provided at http://www.mapequation.org/code.html. |
| Experiment Setup | Yes | For this analysis and the subsequent analysis in Section 7, we set Multlayer Extraction to identify vertex-layer communities that have a large significance score as specified by equation (2). ... The family of communities output by Multilayer Extraction depends on the overlap parameter β [0, 1]. In practice we specify a default value of β by analyzing the number of communities across a grid of β between 0 and 1 in increments of size 0.01. ... Gen Louvain with resolution parameter set to 1, and argument randmove = moverandw. ... Infomap... to permit overlapping communities, and set the algorithm to ignore self-loops. |